skirano commited on
Commit
d847d1d
·
verified ·
1 Parent(s): e5bee48

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,22 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ image-0.png filter=lfs diff=lfs merge=lfs -text
37
+ image-1.png filter=lfs diff=lfs merge=lfs -text
38
+ image-10.png filter=lfs diff=lfs merge=lfs -text
39
+ image-11.png filter=lfs diff=lfs merge=lfs -text
40
+ image-12.png filter=lfs diff=lfs merge=lfs -text
41
+ image-13.png filter=lfs diff=lfs merge=lfs -text
42
+ image-14.png filter=lfs diff=lfs merge=lfs -text
43
+ image-15.png filter=lfs diff=lfs merge=lfs -text
44
+ image-16.png filter=lfs diff=lfs merge=lfs -text
45
+ image-17.png filter=lfs diff=lfs merge=lfs -text
46
+ image-18.png filter=lfs diff=lfs merge=lfs -text
47
+ image-2.png filter=lfs diff=lfs merge=lfs -text
48
+ image-3.png filter=lfs diff=lfs merge=lfs -text
49
+ image-4.png filter=lfs diff=lfs merge=lfs -text
50
+ image-5.png filter=lfs diff=lfs merge=lfs -text
51
+ image-6.png filter=lfs diff=lfs merge=lfs -text
52
+ image-7.png filter=lfs diff=lfs merge=lfs -text
53
+ image-8.png filter=lfs diff=lfs merge=lfs -text
54
+ image-9.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - stable-diffusion-xl
4
+ - stable-diffusion-xl-diffusers
5
+ - text-to-image
6
+ - diffusers
7
+ - lora
8
+ - template:sd-lora
9
+ widget:
10
+ - text: 'A photo of <s0><s1> a bottle of coke '
11
+ output:
12
+ url: image-0.png
13
+ - text: 'A photo of <s0><s1> a bottle of coke '
14
+ output:
15
+ url: image-1.png
16
+ - text: 'A photo of <s0><s1> a bottle of coke '
17
+ output:
18
+ url: image-2.png
19
+ - text: 'A photo of <s0><s1> a bottle of coke '
20
+ output:
21
+ url: image-3.png
22
+ - text: 'A photo of <s0><s1> a bottle of coke '
23
+ output:
24
+ url: image-4.png
25
+ - text: 'A photo of <s0><s1> a bottle of coke '
26
+ output:
27
+ url: image-5.png
28
+ - text: 'A photo of <s0><s1> a bottle of coke '
29
+ output:
30
+ url: image-6.png
31
+ - text: 'A photo of <s0><s1> a bottle of coke '
32
+ output:
33
+ url: image-7.png
34
+ - text: 'A photo of <s0><s1> a bottle of coke '
35
+ output:
36
+ url: image-8.png
37
+ - text: 'A photo of <s0><s1> a bottle of coke '
38
+ output:
39
+ url: image-9.png
40
+ - text: 'A photo of <s0><s1> a bottle of coke '
41
+ output:
42
+ url: image-10.png
43
+ - text: 'A photo of <s0><s1> a bottle of coke '
44
+ output:
45
+ url: image-11.png
46
+ - text: 'A photo of <s0><s1> a bottle of coke '
47
+ output:
48
+ url: image-12.png
49
+ - text: 'A photo of <s0><s1> a bottle of coke '
50
+ output:
51
+ url: image-13.png
52
+ - text: 'A photo of <s0><s1> a bottle of coke '
53
+ output:
54
+ url: image-14.png
55
+ - text: 'A photo of <s0><s1> a bottle of coke '
56
+ output:
57
+ url: image-15.png
58
+ - text: 'A photo of <s0><s1> a bottle of coke '
59
+ output:
60
+ url: image-16.png
61
+ - text: 'A photo of <s0><s1> a bottle of coke '
62
+ output:
63
+ url: image-17.png
64
+ - text: 'A photo of <s0><s1> a bottle of coke '
65
+ output:
66
+ url: image-18.png
67
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
68
+ instance_prompt: A photo of <s0><s1>
69
+ license: openrail++
70
+ ---
71
+
72
+ # SDXL LoRA DreamBooth - skirano/cocacola
73
+
74
+ <Gallery />
75
+
76
+ ## Model description
77
+
78
+ ### These are skirano/cocacola LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
79
+
80
+ ## Download model
81
+
82
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
83
+
84
+ - **LoRA**: download **[`cocacola.safetensors` here 💾](/skirano/cocacola/blob/main/cocacola.safetensors)**.
85
+ - Place it on your `models/Lora` folder.
86
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:cocacola:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
87
+ - *Embeddings*: download **[`cocacola_emb.safetensors` here 💾](/skirano/cocacola/blob/main/cocacola_emb.safetensors)**.
88
+ - Place it on it on your `embeddings` folder
89
+ - Use it by adding `cocacola_emb` to your prompt. For example, `A photo of cocacola_emb`
90
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
91
+
92
+
93
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
94
+
95
+ ```py
96
+ from diffusers import AutoPipelineForText2Image
97
+ import torch
98
+ from huggingface_hub import hf_hub_download
99
+ from safetensors.torch import load_file
100
+
101
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
102
+ pipeline.load_lora_weights('skirano/cocacola', weight_name='pytorch_lora_weights.safetensors')
103
+ embedding_path = hf_hub_download(repo_id='skirano/cocacola', filename='cocacola_emb.safetensors' repo_type="model")
104
+ state_dict = load_file(embedding_path)
105
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
106
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
107
+
108
+ image = pipeline('A photo of <s0><s1>').images[0]
109
+ ```
110
+
111
+ For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
112
+
113
+ ## Trigger words
114
+
115
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
116
+
117
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
118
+
119
+
120
+
121
+ ## Details
122
+ All [Files & versions](/skirano/cocacola/tree/main).
123
+
124
+ The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
125
+
126
+ LoRA for the text encoder was enabled. False.
127
+
128
+ Pivotal tuning was enabled: True.
129
+
130
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
131
+
cocacola.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedbd891cdae2818e429ccff253fa1618a143a6df34aab565ffd490b5521aed4
3
+ size 93148104
cocacola_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a8550fd4363320f47938543d465f839df395f9456ff58c3a6a2fc716aaec86f
3
+ size 16536
image-0.png ADDED

Git LFS Details

  • SHA256: 54a5042bf21e44fbf3e22c047248491657d26bfae8944ab5f885ea077dbc2287
  • Pointer size: 132 Bytes
  • Size of remote file: 1.56 MB
image-1.png ADDED

Git LFS Details

  • SHA256: 48ff6dff5a6a80e9cee75b18d96bacca958b249854cc4d0ee82ca734f72b9a07
  • Pointer size: 132 Bytes
  • Size of remote file: 1.4 MB
image-10.png ADDED

Git LFS Details

  • SHA256: e40c8c3eb6b84488648984227c1c03f9287b6e8126dda28705b9c4d64e16ed0a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.46 MB
image-11.png ADDED

Git LFS Details

  • SHA256: 639e2899b3cb5ff951ffdcdb588990f1083a77880d89f692e0c020d29da2a0f5
  • Pointer size: 132 Bytes
  • Size of remote file: 1.48 MB
image-12.png ADDED

Git LFS Details

  • SHA256: fc8522ef606f7eef2f076094f2b6e55f65fae33e8388e2d30098dfcb40cdc3bc
  • Pointer size: 132 Bytes
  • Size of remote file: 1.44 MB
image-13.png ADDED

Git LFS Details

  • SHA256: a317388944aeed7157d8a1dbd66f4c5a853a49976a9951cc886a43ee03731732
  • Pointer size: 132 Bytes
  • Size of remote file: 1.24 MB
image-14.png ADDED

Git LFS Details

  • SHA256: e5645d4f4ac597e2dd6129ffa358c8ddd567ce92743b19182fc24cad2664652c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.43 MB
image-15.png ADDED

Git LFS Details

  • SHA256: 42ca83ed69b64276fdf4ad8d249ce7894a57d0e6ead1ede581b6eeb37fb956cb
  • Pointer size: 132 Bytes
  • Size of remote file: 1.28 MB
image-16.png ADDED

Git LFS Details

  • SHA256: f6ec0d525f3007ba1854ab74caef79a12a8128120bef75ea0bc4eb400f664413
  • Pointer size: 132 Bytes
  • Size of remote file: 1.48 MB
image-17.png ADDED

Git LFS Details

  • SHA256: be82c6fb47aa4c25790be0f4343b43521c3736b1babb3cb0e44f6ec2cc66a2ec
  • Pointer size: 132 Bytes
  • Size of remote file: 1.36 MB
image-18.png ADDED

Git LFS Details

  • SHA256: 20e92877291e214eac5002a275a7e60924d93af1e94845b2dd3770e4d955c678
  • Pointer size: 132 Bytes
  • Size of remote file: 1.44 MB
image-2.png ADDED

Git LFS Details

  • SHA256: 7b05fbe3b638ec4bf0fdde72aeeb01ed3f9ebde75b86d0ef6faa4b1c211677d8
  • Pointer size: 132 Bytes
  • Size of remote file: 1.43 MB
image-3.png ADDED

Git LFS Details

  • SHA256: bc60f1d8f58a62e0d7f817f3f54272d52b3993995f2a37e46b88b6acf87f0aab
  • Pointer size: 132 Bytes
  • Size of remote file: 1.4 MB
image-4.png ADDED

Git LFS Details

  • SHA256: 382e3c9489e78ce49e7324d672f001e411bd16ad459f1b143b77d945bc9b3c66
  • Pointer size: 132 Bytes
  • Size of remote file: 1.53 MB
image-5.png ADDED

Git LFS Details

  • SHA256: 5a92f3157680f9dbc707a9009e8e71e77f1da553672f71ae6fba287e8ed64b1c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.48 MB
image-6.png ADDED

Git LFS Details

  • SHA256: 6d7e018c5ce58b2238f1a71e245332d0b579361827432b719897f520525a3d30
  • Pointer size: 132 Bytes
  • Size of remote file: 1.4 MB
image-7.png ADDED

Git LFS Details

  • SHA256: 00b4dcbe303ebf39580f4aa88088907ced0fdf1067236b92555b5edfad950aad
  • Pointer size: 132 Bytes
  • Size of remote file: 1.43 MB
image-8.png ADDED

Git LFS Details

  • SHA256: f56f2db2a26d3f2de94c97d9fc2554a9fa9b1c0498d90ca9e9407cb75fc7f43a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.47 MB
image-9.png ADDED

Git LFS Details

  • SHA256: 65ce8fa226a7756ebce6f5808f6d5870cb0ab9f5cdfe79dbb2560ceee21c6f81
  • Pointer size: 132 Bytes
  • Size of remote file: 1.38 MB
logs/dreambooth-lora-sd-xl/1721338956.993372/events.out.tfevents.1721338956.r-skirano-autotrain-cocacola-7kvcd9or-cbf69-lh6r4.194.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe8baa4e4cd0f302c6ae811713265bd744df7b60485b2a7db71c2f0932a9d41
3
+ size 3566
logs/dreambooth-lora-sd-xl/1721338956.994944/hparams.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: true
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 100000
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./5351cb94-5b0e-47ad-8eb8-c6baa9b41ef7
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: true
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: A photo of <s0><s1>
28
+ learning_rate: 1.0
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 0
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 1900
37
+ mixed_precision: bf16
38
+ noise_offset: 0
39
+ num_class_images: 100
40
+ num_new_tokens_per_abstraction: 2
41
+ num_train_epochs: 190
42
+ num_validation_images: 4
43
+ optimizer: prodigy
44
+ output_dir: cocacola
45
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
46
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
47
+ prior_generation_precision: null
48
+ prior_loss_weight: 1.0
49
+ prodigy_beta3: null
50
+ prodigy_decouple: true
51
+ prodigy_safeguard_warmup: true
52
+ prodigy_use_bias_correction: true
53
+ push_to_hub: false
54
+ rank: 16
55
+ repeats: 2
56
+ report_to: tensorboard
57
+ resolution: 1024
58
+ resume_from_checkpoint: null
59
+ revision: null
60
+ sample_batch_size: 4
61
+ scale_lr: false
62
+ seed: 42
63
+ snr_gamma: null
64
+ text_encoder_lr: 1.0
65
+ token_abstraction: TOK
66
+ train_batch_size: 4
67
+ train_text_encoder: false
68
+ train_text_encoder_frac: 1.0
69
+ train_text_encoder_ti: true
70
+ train_text_encoder_ti_frac: 0.5
71
+ use_8bit_adam: false
72
+ validation_epochs: 50
73
+ validation_prompt: null
74
+ variant: null
75
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1721338956.r-skirano-autotrain-cocacola-7kvcd9or-cbf69-lh6r4.194.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e13faf05cc71ad327c577d6dbce8a41ae415cb1d3b6010f3d430b0721b2ef9
3
+ size 159434
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd101019ec5e5ea0a72a7f151690af3bbd61f6db01926e765e416d4383afe72d
3
+ size 93065304